agentleFS
snui1ssnui1s/losna-cli/skills/file-editing/SKILL.MD

file-editing

Skill1 starsChanged 2 months agoApache-2.0View on GitHub

1. FILE EDITING & TRUST: When you use the 'edit_local_file' or 'replace_in_file' tools to modify content, trust the success message returned by the tool. Do NOT call 'read_local_file', 'view_file_lines', or 'list_directory' immediately afterward to verify your action. Once the tool returns a success status, consider the task complete and reply to the user immediately. 2. TARGETED MODIFICATIONS: When asked to modify a specific function, variable, or block of code within an existing file, prefer using 'replace_in_file' over 'edit_local_file' to avoid…

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    NOT call 'read_local_file', 'view_file_lines', or 'list_directory' immediately afterward to verify your action.

    line 8
  2. Distinctive:

    Before calling 'replace_in_file', make sure the 'old_text' you pass matches the file's actual current content exactly - if you haven't read …

    line 19

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.MD

File Editing Skill

Description: Use this whenever asked to modify, edit, update, or change content in an existing file.

Rules for this task

  1. FILE EDITING & TRUST: When you use the 'edit_local_file' or 'replace_in_file' tools to modify content, trust the success message returned by the tool. Do NOT call 'read_local_file', 'view_file_lines', or 'list_directory' immediately afterward to verify your action. Once the tool returns a success status, consider the task complete and reply to the user immediately.
  2. TARGETED MODIFICATIONS: When asked to modify a specific function, variable, or block of code within an existing file, prefer using 'replace_in_file' over 'edit_local_file' to avoid accidentally destroying other parts of the file. Only use 'edit_local_file' (which overwrites/appends) when the user wants to replace the entire file content or append a new block, not when editing a specific existing part.
  3. Before calling 'replace_in_file', make sure the 'old_text' you pass matches the file's actual current content exactly - if you haven't read the file yet in this task, read the relevant section first so the replacement doesn't silently fail to match.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.